https://github.com/nikhilbarhate99/actor-critic-pytorch

Policy Gradient Actor-Critic PyTorch | Lunar Lander v2
https://github.com/nikhilbarhate99/actor-critic-pytorch

a2c actor-critic deep-reinforcement-learning openai-gym openai-gym-environments policy-gradient pytorch pytorch-implmention pytorch-tutorial reinforcement-learning-algorithms

Last synced: 4 days ago
JSON representation

Policy Gradient Actor-Critic PyTorch | Lunar Lander v2

• Host: GitHub
• URL: https://github.com/nikhilbarhate99/actor-critic-pytorch
• Owner: nikhilbarhate99
• License: bsd-3-clause
• Created: 2018-09-03T11:34:40.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2019-05-07T07:50:26.000Z (over 5 years ago)
• Last Synced: 2024-01-29T23:13:40.435Z (10 months ago)
• Topics: a2c, actor-critic, deep-reinforcement-learning, openai-gym, openai-gym-environments, policy-gradient, pytorch, pytorch-implmention, pytorch-tutorial, reinforcement-learning-algorithms
• Language: Python
• Homepage:
• Size: 2.1 MB
• Stars: 65
• Watchers: 1
• Forks: 27
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Actor-Critic

Solution for Lunar Lander environment v2 of Open AI gym.

The algorithm used is actor-critic (vanilla policy gradient with baseline),

more info : http://rail.eecs.berkeley.edu/deeprlcourse-fa17/f17docs/lecture_5_actor_critic_pdf.pdf

-> Dependencies:

        OpenAI gym

        PyTorch 0.4.1

        PIL

-> Hyperparameters can be changed by editing them in respective files

-> To train : run train.py

-> Converges within 1500 episodes

-> To test a pretrained model : run test.py

![alt-text](https://github.com/nikhilbarhate99/Actor-Critic/blob/master/gif/gif3.gif)